fix stage 2 and 3

This commit is contained in:
Kinan Martin 2025-05-01 08:15:07 +09:00
parent 90326c1f43
commit 88249f0eb4

View File

@ -71,7 +71,10 @@ if [ $stage -le 2 ] && [ $stop_stage -ge 2 ]; then
log "Stage 2: Prepare transcript for BPE training"
if [ ! -f data/lang/transcript.txt ]; then
log "Generating transcripts for BPE training"
./local/utils/generate_transcript.py --lang-dir data/lang
python local/utils/generate_transcript.py \
--dataset-path $dl_dir/mls_english \
--lang-dir data/lang \
--split train
fi
fi
@ -83,7 +86,7 @@ if [ $stage -le 3 ] && [ $stop_stage -ge 3 ]; then
mkdir -p $bpe_dir
if [ ! -f $bpe_dir/bpe.model ]; then
./local/train_bpe_model.py \
python local/train_bpe_model.py \
--lang-dir $bpe_dir \
--vocab-size $vocab_size \
--transcript data/lang/transcript.txt